Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nvidia announces financial results for second quarter fiscal 2024

nvidianews.nvidia.com

Post reply on HN
Print view View original

331–340 of 444 posts

Re: Nvidia announces financial results for second quarter fiscal 2024

#331

Post by hinoki »

dekhn wrote: post #206
desiarnezjr wrote: post #194

Earlier quoted context omitted.

I remember meeting NVIDIA in the late aughts (2007?) first launching their CUDA efforts. Really the product was a re-branded 780GTX or whatever their high end gaming card was at the time more or less, but they already laid out a clear pathway to today (more or less).

I remember meeting with them in the mid aughts when they were first talking to HPC folks about using their cards for science. I'll never forget what the chief scientist from nVidia said. "What is the color of a NaN? That is, when you render a texture with a nan value, what does it look like? I'll tell: it's nvidia green."

32-bit NaN is encoded: s111 1111 1xxx xxxx xxxx xxxx xxxx xxxx

Where both the sign (s) and the x bits can be anything and it will still be treated as a NaN.

There are lots of ways to encode colour, but there would be too much red with RGBA, and ARGB could be almost any opaque colour, but the red channel has to be at least 0x80, which is still too much red.

So NaNs are too red to encode nvidia green.

Re: Nvidia announces financial results for second quarter fiscal 2024

#332

Post by distances »

sgarman wrote: post #149
Mountain_Skies wrote: post #55

Earlier quoted context omitted.

For much of tech hardware world, declining costs and increasing performance have been the general trends for as long as most of us have been alive.

Off the top of my head the only thing I can think of that did that was TVs.

As far as I can tell computers are still cheaper than they were in the 90s. And that's in absolute numbers, not even accounting for inflation.

Re: Nvidia announces financial results for second quarter fiscal 2024

#333

Post by redox99 »

gmm1990 wrote: post #264
gen220 wrote: post #255

How durable do we think their Revenue is? To remind us all, they're selling capitalized assets, not contracts or services. Is the marginal demand for GPU chips over the next 3 years enough to sustain (or grow?) current revenues and keep this valuation afloat? To me, it feels like a comparatively fragile situation to find themselves in, to convince the world of 2025 that they need even more chips , unless "everybody n…

It seems pretty similar to Tesla’s valuation with a product that won’t be as sticky as electric cars

They are not similar at all. Tesla P/E is 67, Nvidia's P/E is 244.

Re: Nvidia announces financial results for second quarter fiscal 2024

#334

Post by AaronFriel »

radium3d wrote: post #313
ATMLOTTOBEER wrote: post #275

Earlier quoted context omitted.

Fps in CSGO isn’t really so dependent on the GPU as more modern games, so comparing with a different game might be more accurate.

I'm curious, do you know of a study that has proven that single core CPU or other is the bottleneck in CS:GO?

This is essentially folk wisdom - but I think you can trust the other people in this thread that it's accurate. I doubt anyone has done a scientific study on this, but you could see this for yourself by setting your computer's clock rate lower and re-running the benchmark.

I expect that if you have a 4090, you have an Intel or AMD CPU that exposes a core clock multiplier. You could run this benchmark with whatever value it's at, then reduce the modifier by say, half. That should halve your CPU's clock rate, and I'm guessing you'll see the frame rate decline similarly. You can conclude that the game is "CPU bound", then.

Even if your GPU was infinitely fast, you have to remember that game developers are not optimizing for the game event loop to run in sub-millisecond times. If the core loop in the game takes under 16ms to run on a common CPU, such as one in a console: that's better than 60hz and the overwhelming majority of video game players will never see a benefit.

Some game developers, I see someone in another thread mentioned Doom Eternal, pride themselves on that optimization. With a fast enough CPU and GPU, you could probably reach 1000 FPS on Doom Eternal. A quick search suggests this might have been accomplished with a liquid cooled, this was done with a liquid nitrogen cooled PC with a 6.6GHz CPU: https://www.pcgamer.com/heres-doom-eternal-running-at-1000-f...

Re: Nvidia announces financial results for second quarter fiscal 2024

#335

Post by Toutouxc »

izacus wrote: post #328
ken47 wrote: post #184

Earlier quoted context omitted.

Until very recently, AMD was struggling for survival. Rather than making the big bet on AI, they went for the sure thing by banking on revolutionary CPU tech. I'm sure if they were in a better financial position 5 years ago, they would have gone bigger on AI.

They also focused on game consoles, where they won contracts for both major platforms this generation.

Previous one too. Xbox One and Series and PS4 and PS5 are all AMD, and there’s several revisions of each (e.g. PS4 OG, Slim, Pro).

Re: Nvidia announces financial results for second quarter fiscal 2024

#337

Post by zirgs »

izacus wrote: post #328
ken47 wrote: post #184

Earlier quoted context omitted.

Until very recently, AMD was struggling for survival. Rather than making the big bet on AI, they went for the sure thing by banking on revolutionary CPU tech. I'm sure if they were in a better financial position 5 years ago, they would have gone bigger on AI.

They also focused on game consoles, where they won contracts for both major platforms this generation.

The other non-major Nvidia based console has higher sales numbers than both of so-called major consoles combined.

Re: Nvidia announces financial results for second quarter fiscal 2024

#338

Post by redox99 »

wudangmonk wrote: post #76
TechnicolorByte wrote: post #22

Earlier quoted context omitted.

Nvidia is dragging the entire gaming industry forward with ray/path tracing and AI-based resolution and frame scaling. Everyone else (I.e., AMD) is following Nvidia’s lead. In what way has Nvidia “forgotten” gamers with the rise of their datacenter business?

Raytracing isn't a thing no matter how much nvidia wants to push it. The performance penalty is too big for what amounts to something that takes a trained eye to notice. AI-resolution scaling is nice to have on lower end devices but the max resolution people actually use is 4k and I can only think of VR where having more than 4k would be nice to have. My main gripe is that at 4k resolution, top of the line GPUs shoul…

This comment will age like milk, when in a few years (nvidia 50 series I'd say) path tracing becomes the norm for high end gaming.

Re: Nvidia announces financial results for second quarter fiscal 2024

#339

Post by jacooper »

fleischhauf wrote: post #201
edgyquant wrote: post #180

Earlier quoted context omitted.

100% this. I, and many others, bought multiple AMD cards due to disliking NVidia and tried to get ROCm set up to no avail. It just never worked except under hard to maintain configurations. I switched to an nvidia card and within the hour import tensorflow just worked

to be fair Nvidia drivers are also a nightmare under linux

Not anymore

Re: Nvidia announces financial results for second quarter fiscal 2024

#340

Post by andersa »

hinoki wrote: post #331
dekhn wrote: post #206

Earlier quoted context omitted.

I remember meeting with them in the mid aughts when they were first talking to HPC folks about using their cards for science. I'll never forget what the chief scientist from nVidia said. "What is the color of a NaN? That is, when you render a texture with a nan value, what does it look like? I'll tell: it's nvidia green."

32-bit NaN is encoded: s111 1111 1xxx xxxx xxxx xxxx xxxx xxxx Where both the sign (s) and the x bits can be anything and it will still be treated as a NaN. There are lots of ways to encode colour, but there would be too much red with RGBA, and ARGB could be almost any opaque colour, but the red channel has to be at least 0x80, which is still too much red. So NaNs are too red to encode nvidia green.

I once ended up having nans get interpreted as 32 bit colors accidentally, and it made everything red and white, like Christmas decoration.

Wonder what caused the difference in the latter bits being all 1 or 0 together.

Post reply on HN